Agent Harness
The Harness is the core of cascadeflow’s runtime intelligence. It wraps agent execution and decides whether a model call should proceed, switch models, remove tools, or stop.What the Harness Does
At every LLM call or tool execution inside an agent loop, the Harness:- Checks hard constraints: Budget remaining, compliance allowlist, tool-call cap, latency limit, and energy limit.
- Scores soft dimensions: Quality, cost, latency, and energy weighted by KPI priorities.
- Decides an action:
allow,switch_model,deny_tool, orstop. - Records a trace: Action, reason, model, step, cost, and budget state.
observe mode, decisions are recorded but not enforced. In enforce mode, they shape execution in real time.
HarnessConfig
Harness behavior is configured through one language-specific object.The Three-Tier API
cascadeflow offers three levels of control. Use the one that fits your needs.Tier 1: Global Init (Zero-Change)
Tier 2: Scoped Run (Block-Level Control)
Tier 3: Agent Decorator (Per-Agent Policy)
run() when the policy must be enforced.
Decision Priority
When the Harness evaluates a step, it follows a strict priority order:
Hard constraints (budget, compliance) always take priority over soft scoring (KPI weights).
Six Dimensions at a Glance
Observe vs Enforce
Start with
observe to validate your policies against real traffic. Switch to enforce when you are confident the rules are correct.